SKILLEMALL.ai

FB openclaw-nextcloud

Manage Notes, Tasks, Calendar, Files, Contacts, and Deck Kanban boards in your Nextcloud instance via CalDAV, WebDAV, Notes, and Deck APIs. Use for creating notes, managing todos and calendar events, uploading/downloading files, managing contacts, and organizing Kanban boards, stacks, and cards.

Blockedguard blocked the skill: signs of malicious behaviour
ClawHub Agent Skills author: Keith Vassallo v0.6.0 MIT-0 6 files body ≈ 5 272 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process B 76/100 · Nearly there — weak spots: running it twice, progress reporting

GeneratorPersonal productivitytype and topics are labelled automatically from the skill text
JSON
Technical rating
F
36/100
safety, quality, tests
Safety 60%
10
Quality 40%
75
Run on models
none yet
Process rating
B
76/100
Nearly there
Progress reporting w 2
0
Running it twice w 4
30
When it triggers w 12
50
the three weakest of ten parameters · all ten
Guard blocked this skill: critical findings below. Do not install it until the author fixes them.

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Exfiltration
If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. Remove the critical guard findings (secrets, dangerous commands, hidden instructions): while they stand the skill is blocked and cannot grade above F.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 6

  • critical Exfiltration exfil-send-secrets-to-url index.js:60
    Instruction to send secrets/history to an external endpoint (quoted — discussed, not commanded)
    message: `Refusing to send credentials over '${parsed.protocol}//' to '${parsed.host}'. Use https:// or set OPENCLAW_ALLOW_HTTP=1 to override (not recommended).`
    quoted
Medium and low: 5
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Bash Read
  • low Secrets in code secret-high-entropy-token package-lock.json:84
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…S4F+im88…HRE/cYlx…2oE/ufM0p61IKng==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:135
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…rdY+ziCYCPMmtZjjIwOmXFjmyzEHn+UUxk5of+SYsj…5hY/rOAw==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:220
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…NmN+loZK…eAz+famM…vZz+zT1jlh/keC3Rj/lg==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:623
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…SN2+yCV/fTW3…TGk+dvvn…Mwg==",
    detector

Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5272 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 76/100

  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 101 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 60Result and completion. Output format stated, no completion criterion
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Failures and branches. 10 branches
  • 70Execution cost. Instruction body is 5272 tokens
  • 100Tools and files. Tools declared in frontmatter
  • 100Steps. 135 steps
  • 100Consistency. Name and required fields are in place
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 11 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (28 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • -226 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +3Description length 296: enough signal without eating the budget
  • +4Structure: 49 headings
  • +3Step-by-step instructions: 135 items
  • +3Output format is stated explicitly
  • +4Has examples (14 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.

External checks

ClawHub: clean
This Nextcloud skill has broad account access, but its credentials, network use, destructive actions, and public-sharing capability are disclosed and mostly guarded.
LLM: benign (high) · VirusTotal: · 10 Sept 2026